Child-directed speech facilitates production, not comprehension, in BabyLMs

• URL: http://arxiv.org/abs/2606.01045v1
• Date: Sun, 31 May 2026 06:27:58 GMT
• Title: Child-directed speech facilitates production, not comprehension, in BabyLMs
• Abstract summary: We introduce a novel generation-based evaluation inspired by usage-based theories of language acquisition.<n>We compare Llama models trained with CDS, the BabyLM corpus, and web-crawl data (FineWeb-edu) on comprehension benchmarks and our novel framework.<n>Our results reveal a clear dissociation between models' comprehension and production capabilities.
• Score: 10.0983193189508
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent studies suggest that child-directed speech is not conducive to language learning in BabyLMs. However, current evaluations focus predominantly on comprehension and not production, which is central to usage-based theories of language acquisition which argue how CDS facilitates early language use through constructional ''frames'' (frequent lexical patterns with open slots). We introduce a novel generation-based evaluation inspired by such theories in form of a frame-completion task, and compare Llama models trained with CDS, the BabyLM corpus, and web-crawl data (FineWeb-edu) on comprehension benchmarks and our novel framework. Our results reveal a clear dissociation between models' comprehension and production capabilities: while FineWeb-trained models excel at minimal pairs, CDS-trained models produce grammatical completions substantially earlier in training and concentrate probability mass on appropriate slot-fillers. These findings show that comprehension benchmarks underestimate what CDS affords to BabyLMs.

Related papers

• From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment [12.134587575174633]
  We propose a general framework for sentence-level interpretability of rubric-based scoring.<n>We show that SHAP provides more faithful and transferable explanations for rubric-based scoring.
  arXiv  Detail & Related papers  (2026-04-18T14:27:51Z)
• Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet [72.53502346791814]
  We compare flat-start training across datasets, SSL representations (WavLM, XEUS), and decoder architectures.<n> SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases.<n>Age-related ASR and speaker verification analysis highlights the limitations of proprietary models.
  arXiv  Detail & Related papers  (2025-08-22T17:59:35Z)
• Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models [49.1574468325115]
  We introduce Speech-IFeval, an evaluation framework designed to assess instruction-following capabilities.<n>Recent SLMs integrate speech perception with large language models (LLMs), often degrading textual capabilities due to speech-centric training.<n>Our findings show that most SLMs struggle with even basic instructions, performing far worse than text-based LLMs.
  arXiv  Detail & Related papers  (2025-05-25T08:37:55Z)
• BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning [33.64851748019174]
  Human infants rapidly develop visual reasoning skills from minimal input.<n>Recent efforts have leveraged infant-inspired datasets like SAYCam.<n>We propose BabyVLM, a novel framework comprising comprehensive in-domain evaluation benchmarks and a synthetic training dataset.
  arXiv  Detail & Related papers  (2025-04-13T04:17:12Z)
• BAMBI: Developing Baby Language Models for Italian [45.36413940519089]
  This paper presents BAMBI (BAby language Models Boostrapped for Italian), a series of Baby Language Models (BabyLMs) trained on data that mimic the linguistic input received by a five-year-old Italian-speaking child.<n>The BAMBI models are tested using a benchmark specifically designed to evaluate language models, which takes into account the amount of training input the models received.
  arXiv  Detail & Related papers  (2025-03-12T15:36:50Z)
• MACT: Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing [4.536003573070846]
  We introduce a cross-lingual training strategy for semantic representation parsing models. It exploits the alignments between languages encoded in pre-trained language models. Experiments show significant improvements in DRS clause and graph parsing in English, German, Italian and Dutch.
  arXiv  Detail & Related papers  (2024-06-03T07:02:57Z)
• InstructionCP: A fast approach to transfer Large Language Models into target language [55.2480439325792]
  InsCP integrates instruction tags into the CP process to prevent loss of conversational proficiency while acquiring new languages. Our experiments demonstrate that InsCP retains conversational and Reinforcement Learning from Human Feedback abilities. This approach requires only 0.1 billion tokens of high-quality instruction-following data, thereby reducing resource consumption.
  arXiv  Detail & Related papers  (2024-05-30T15:45:13Z)
• Evaluating Neural Language Models as Cognitive Models of Language Acquisition [4.779196219827507]
  We argue that some of the most prominent benchmarks for evaluating the syntactic capacities of neural language models may not be sufficiently rigorous. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition.
  arXiv  Detail & Related papers  (2023-10-31T00:16:17Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• SINC: Self-Supervised In-Context Learning for Vision-Language Tasks [64.44336003123102]
  We propose a framework to enable in-context learning in large language models. A meta-model can learn on self-supervised prompts consisting of tailored demonstrations. Experiments show that SINC outperforms gradient-based methods in various vision-language tasks.
  arXiv  Detail & Related papers  (2023-07-15T08:33:08Z)
• Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little [74.49773960145681]
  A possible explanation for the impressive performance of masked language model (MLM)-training is that such models have learned to represent the syntactic structures prevalent in NLP pipelines. In this paper, we propose a different explanation: pre-trains succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. Our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
  arXiv  Detail & Related papers  (2021-04-14T06:30:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.